# Jev Use

> Use before ANY step that is a decision rather than writing: labelling, filtering or triaging MANY items; checking whether a command, test or build succeeded; picking the next action from options you can list; judging safety, quality or severity; or risk-checking each command of a checklist or pipeline before it runs. Route by where the facts already are: facts already in your context go to the je…

- **Type:** Skill
- **Install:** `agentstack add skill-shitianfang-jev-use-jev-use`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [shitianfang](https://agentstack.voostack.com/s/shitianfang)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [shitianfang](https://github.com/shitianfang)
- **Source:** https://github.com/shitianfang/jev-use/tree/main/skills/jev-use
- **Website:** https://www.npmjs.com/package/jev-use

## Install

```sh
agentstack add skill-shitianfang-jev-use-jev-use
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Handing off to Jev

Jev answers a typed judgment in ~250 ms at a judgment-model rate ($0.042/Mtok
in, $0 out) instead of LLM reasoning. It is a RATE win, not a token win: Jev
spends *more* tokens per decision, not fewer. So the saving is real only when
the decision **leaves the conversation** — which is what the routing below is
for. You stay the planner and the writer.

## Route each decision: where are the facts × does it block?

| Where the facts are | **Nothing is blocked** — you can keep working | **Blocked** — nothing proceeds until this is decided |
| --- | --- | --- |
| **Already in your context** | `jev_judge`, every question about that state batched into **ONE** call (`noul` yes/no, `choice` next action, `score` quality) | `jev_gate` on that one action before you run it — and if it is *every* tool call, wire `jev-use hook gate` as a PreToolUse hook **once** and the decision leaves the conversation for good: 24 gated commands, 17.1 s, **zero LLM tokens**, vs 46.9 s / $0.2366 through a supervisor LLM |
| **Sitting in a file or tool output** | a script pipes the file to `jev-use judge` — the items never enter your context | same CLI, from the script, then act on the verdicts it prints |
| **To be written by you** (new text, code, options you cannot enumerate) | yours | yours |

## Rules that make it pay off

- **Route bulk data by reference.** When the items sit in a file or in tool
  output, have a script pipe them to `jev-use judge` — data pasted into a
  `jev_judge` call travels through your context twice, as tool input and as
  the verdict block back. Or route only the handful you genuinely cannot
  settle yourself.
- **Batch.** Measured: 12 questions about one state in ONE call took 224 ms;
  the same 12 one at a time took 2,662 ms. Never one call per item.
- **State is everything Jev sees.** Put the relevant facts (tool output, file
  excerpts, task intent) into `state`; Jev has no other context.
- **Honor escalations.** A verdict with `escalate: true` hands that question
  back to you: `writing`/`open_ended` mean it was structurally yours;
  `oversized` means the state was too big to judge; `unsure` means Jev's
  answer is only a prior (it's still in `answer` — use it as a hint);
  `unreachable` means proceed as if Jev didn't exist.
- **Don't route trivia.** If you already know the answer, just act; a Jev
  call you didn't need is still a call.

Numbers, lanes, variance and caveats: `bench/RESULTS.md`.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [shitianfang](https://github.com/shitianfang)
- **Source:** [shitianfang/jev-use](https://github.com/shitianfang/jev-use)
- **License:** MIT
- **Homepage:** https://www.npmjs.com/package/jev-use

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-shitianfang-jev-use-jev-use
- Seller: https://agentstack.voostack.com/s/shitianfang
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.